Search Results (48)

Early prediction of lymph node metastasis (LNM) following neoadjuvant therapy (NAT) is crucial for timely treatment optimization in esophageal squamous cell carcinoma (ESCC). This study developed and validated a computed tomography-based radiomic model for predicting pathologically confirmed LNM status at the time of surgery in ESCC patients after NAT. A total of 469 ESCC patients from Sun Yat-sen University Cancer Center were retrospectively enrolled and randomized into a training cohort (n = 328) and a test cohort (n = 141). Three signatures were constructed: the tumor-habitat-based signature (Habitat_Rad), derived from radiomic features of three tumor subregions identified via K-means clustering; the multiple instance learning-based signature (MIL_Rad), combining features from 2.5D deep learning models; and the clinicoradiological signature (Clinic), developed through multivariate logistic regression. A combined radiomic nomogram integrating these signatures outperformed the individual models, achieving areas under the curve (AUCs) of 0.929 (95% CI, 0.901–0.957) and 0.852 (95% CI, 0.778–0.925) in the training and test cohorts, respectively. The decision curve analysis confirmed a high net clinical benefit, highlighting the nomogram’s potential for accurate LNM prediction after NAT and guiding individualized therapy. Full article

Background: This study aimed to develop a nomogram based on the most relevant clinical, CT, and radiomic features comprising 11 key signatures (2 clinical, 2 CT-based, and 7 radiomic) for the non-invasive prediction of the EGFR mutation status and to support the timely initiation of tyrosine kinase inhibitor (TKI) therapy in patients with non-small cell lung cancer (NSCLC) adenocarcinoma. Methods: Retrospective real-world data were collected from 521 patients with histologically confirmed NSCLC adenocarcinoma who underwent CT imaging and either surgical resection or pathological biopsy for EGFR mutation testing. Five Random Forest classification models were developed and trained on various datasets constructed by combining clinical, CT, and radiomic features extracted from CT image regions of interest (ROIs), with and without feature preselection. Results: The model trained exclusively on the most relevant clinical, CT, and radiomic features demonstrated superior predictive performance compared to the other models, with strong discrimination between EGFR-mutant and wild-type cases (AUC = 0.88; macro-average = 0.90; micro-average = 0.89; precision = 0.90; recall = 0.94; F1-score = 0.91; and accuracy = 0.87). Conclusions: A nomogram constructed using a Random Forest model trained solely on the most informative clinical, CT, and radiomic features outperformed alternative approaches in the non-invasive prediction of the EGFR mutation status, offering a promising decision-support tool for precision treatment planning in NSCLC. Full article

Background/Objectives: To develop a nomogram for predicting tumor aggressiveness and the presence of lymphovascular space involvement (LVSI) in patients with endometrial cancer (EC) using preoperative MRI and pathology–laboratory data. Methods: This IRB-approved, retrospective, multicenter study included 245 patients with histologically confirmed EC who underwent preoperative MRI and surgery at participating institutions between January 2020 and December 2024. Tumor type and grade, both from preoperative biopsy and surgical specimens, as well as preoperative CA125 and HE4 levels, were retrieved from institutional databases. A preoperative MRI was used to assess tumor morphology (polypoid vs. infiltrative), maximum diameter, presence and depth (< or >50%) of myometrial invasion, cervical stromal invasion (yes/no), and minimal tumor-to-serosa distance. The EC-to-uterus volume ratio was also calculated. Results: Among the 245 patients, 27% demonstrated substantial LVSI, and 35% were classified as aggressive on final histopathology. Multivariate analysis identified independent MRI predictors of LVSI, including cervical stromal invasion (OR = 9.06; p = 0.0002), tumor infiltration depth (OR = 2.09; p = 0.0391), and minimal tumor-to-serosa distance (OR = 0.81; p = 0.0028). The LVSI prediction model yielded an AUC of 0.834, with an overall accuracy of 78.4%, specificity of 92.2%, and sensitivity of 43.1%. For tumor aggressiveness prediction, significant predictors included biopsy grade (OR = 8.92; p < 0.0001), histological subtype (OR = 12.02; p = 0.0021), and MRI-detected serosal involvement (OR = 14.39; p = 0.0268). This model achieved an AUC of 0.932, with an accuracy of 87.0%, sensitivity of 79.8%, and specificity of 91.2%. Both models showed excellent calibration (Hosmer–Lemeshow p > 0.86). Conclusions: The integration of MRI-derived morphological and quantitative features with clinical and histopathological data allows for effective preoperative risk stratification in endometrial cancer. The two nomograms developed for predicting LVSI and tumor aggressiveness demonstrated high diagnostic performance and may support individualized surgical planning and decision-making regarding adjuvant therapy. These models are practical, reproducible, and easily applicable in standard clinical settings without the need for radiomics software, representing a step toward more personalized gynecologic oncology. Full article

Background: A micropapillary pattern (MP) and solid pattern (SP) in lung adenocarcinoma (LUAD), a major subtype of non-small-cell lung cancer (NSCLC), are associated with a poor prognosis and necessitate accurate preoperative identification. This study aimed to develop and validate a predictive model combining clinical and radiomics features for differentiating a high-risk MP/SP in LUAD. Methods: This retrospective study analyzed 180 surgically confirmed NSCLC patients (Stages I–IIIA), randomly divided into training (70%, n = 126) and validation (30%, n = 54) cohorts. Three prediction models were constructed: (1) a clinical model based on independent clinical and CT morphological features (e.g., nodule size, lobulation, spiculation, pleural indentation, and vascular abnormalities), (2) a radiomics model utilizing LASSO-selected features extracted using 3D Slicer, and (3) a comprehensive model integrating both clinical and radiomics data. Results: The clinical model yielded AUCs of 0.7975 (training) and 0.8462 (validation). The radiomics model showed superior performance with AUCs of 0.8896 and 0.8901, respectively. The comprehensive model achieved the highest diagnostic accuracy, with training and validation AUCs of 0.9186 and 0.9396, respectively (DeLong test, p < 0.05). Decision curve analysis demonstrated the enhanced clinical utility of the combined approach. Conclusions: Integrating clinical and radiomics features significantly improves the preoperative identification of aggressive NSCLC patterns. The comprehensive model offers a promising tool for guiding surgical and adjuvant therapy decisions. Full article

Objectives: Differentiation of adrenal incidentalomas (AIs) remains a challenge in the oncological setting. The aim of the study was to explore the diagnostic efficacy of [18F]Fluorodeoxyglucose (FDG) positron emission tomography combined with computed tomography (PET/CT)-based radiomics in identifying adrenal metastases and to compare it with that of conventional PET/CT parameters. Materials: Retrospective analysis was performed on 195 AIs for model construction, nomogram drawing, and internal validation. An additional 30 AIs were collected for external validation of the radiomics model and nomogram. Logistic regression analysis was employed to build models based on clinical and PET/CT routine parameters. The open-source software Python (version 3.7.11) was utilized to process the regions of interest (ROI) delineated by ITK-SNAP, extracting radiomic features. Least absolute shrinkage and selection operator (LASSO) regression analysis was applied for feature selection. Based on the selected features, the optimal model was chosen from ten machine learning algorithms, and the nomogram was constructed. Results: The area under the curve (AUC), sensitivity, specificity, and accuracy of conventional parameters of PET/CT were 0.919, 0.849, 0.892, and 0.844, respectively. XGBoost demonstrated superior diagnostic efficiency among the radiomics models, outperforming those constructed using independent predictors. The AUC, accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of XGBoost’s internal and external validation were 0.945, 0.932, 0.930, 0.960, 0.970, 0.890 and 0.910, 0.900, 0.860, 1, 1, 0.750. The accuracy, sensitivity, specificity, PPV, and NPV of the nomogram in external validation were 0.870, 0.952, 0.667, 0.870, and 0.857. Conclusions: The radiomics model and conventional PET/CT parameters both showed high diagnostic performance (AUC p > 0.05) in discriminating adrenal metastases from benign lesions, offering a practical, non-invasive approach for clinical assessment. Full article

Objective: The primary objective of this study was to develop and validate a predictive nomogram that integrates radiomic features derived from contrast-enhanced computed tomography (CECT) images with clinical variables to predict overall survival (OS) in patients with hepatocellular carcinoma (HCC) after surgical resection. Methods: This retrospective study analyzed the preoperative enhanced CT images and clinical data of 202 patients with HCC who underwent surgical resection at the Affiliated Hospital of North Sichuan Medical College (Institution 1) from June 2017 to June 2021 and at Nanchong Central Hospital (Institution 2) from June 2020 to June 2022. Among these patients, 162 patients from Institution 1 were randomly divided into a training cohort (112 patients) and an internal validation cohort (50 patients) at a 7:3 ratio, whereas 40 patients from Institution 2 were assigned as an independent external validation cohort. Univariate and multivariate Cox proportional hazards regression analyses were performed to identify clinical risk factors associated with OS after HCC resection. Using 3D-Slicer software, tumor lesions were manually delineated slice by slice on preoperative non-contrast-enhanced (NCE) CT, arterial phase (AP), and portal venous phase (PVP) images to generate volumetric regions of interest (VOIs). Radiomic features were subsequently extracted from these VOIs. LASSO Cox regression analysis was employed for dimensionality reduction and feature selection, culminating in the construction of a radiomic signature (Radscore). Cox proportional hazards regression models, including a clinical model, a radiomic model, and a radiomic–clinical model, were subsequently developed for OS prediction. The predictive performance of these models was assessed via the concordance index (C-index) and time–ROC curves. The optimal performance model was further visualized as a nomogram, and its predictive accuracy was evaluated via calibration curves and decision curve analysis (DCA). Finally, the risk factors in the optimal performance model were interpreted via Shapley additive explanations (SHAP). Results: Univariate and multivariate Cox regression analyses revealed that BCLC stage, the albumin–bilirubin index (ALBI), and the NLR–PLR score were independent predictors of OS after HCC resection. Among these three models, the radiomic–clinical model exhibited the highest predictive performance, with C-indices of 0.789, 0.726, and 0.764 in the training, internal and external validation cohorts, respectively. Furthermore, the time–ROC curves for the radiomic–clinical model showed 1-year and 3-year AUCs of 0.837 and 0.845 in the training cohort, 0.801 and 0.880 in the internal validation cohort, and 0.773 and 0.840 in the external validation cohort. Calibration curves and DCA demonstrated the model’s excellent calibration and clinical applicability. Conclusions: The nomogram combining CECT radiomic features and clinical variables provides an accurate prediction of OS after HCC resection. This model is beneficial for clinicians in developing individualized treatment strategies for patients with HCC. Full article

Objectives: The preoperative identification of occult pleural metastasis (OPM) in lung cancer remains a crucial clinical challenge. This study aimed to develop and validate a predictive model that integrates clinical information with chest CT radiomic features to preoperatively identify patients at risk of OPM. Methods: This study included 50 patients diagnosed with OPM during surgery as the positive training cohort and an equal number of nonmetastatic patients as the negative control cohort. Using least absolute shrinkage and selection operator (LASSO) logistic regression, we identified key radiomic features and calculated radiomic scores. A predictive nomogram was developed by combining clinical characteristics and radiomic scores, which was subsequently validated with data from an additional 545 patients across three medical centers. Results: Univariate and multivariate logistic regression analyses revealed that carcinoembryonic antigen (CEA), the neutrophil-to-lymphocyte ratio (NLR), the clinical T stage, and the tumor–pleural relationship were significant clinical predictors. The clinical model alone achieved an area under the curve (AUC) of 0.761. The optimal integrated model, which combined radiomic scores from the volume of interest (VOI) with the CEA and NLR, demonstrated an improved predictive performance, with AUCs of 0.890 in the training cohort and 0.855 in the validation cohort. Conclusions: Radiomic features derived from CT scans show significant promise in identifying patients with lung cancer at risk of OPM. The nomogram developed in this study, which integrates CEA, the NLR, and radiomic tumor area scores, enhances the precision of preoperative OPM prediction and provides a valuable tool for clinical decision-making. Full article

Introduction: Glioma Grade 4 (GG4) tumors, which include both IDH-mutated and IDH wild-type astrocytomas, are the most prevalent and aggressive form of primary brain tumor. Radiomics is gaining ground in neuro-oncology. The integration of this data into machine learning models has the potential to improve the accuracy of prognostic models for GG4 patients. Karnofsky Performance Status (KPS), an established preoperative prognostic factor for survival, is commonly used in these patients. In this study, we developed a nomogram to identify patients with improved functional performance as indicated by an increase in KPS after surgery by analyzing radiomic features from preoperative 3D MRI scans. Methods: Quantitative imaging features were extracted from the -3D T1 GRE sequence of 157 patients from a single center and were used to develop the machine learning (ML) model. To improve applicability and create a nomogram, multivariable logistic regression analysis was performed to build a model incorporating clinical characteristics and radiomics features. Results: We labeled 55 cases in which KPS was improved after surgery (35%, KPS-flag = 1). The resulting model was evaluated according to test series results. The best model was obtained by XGBoost using the features extracted by pyradiomics, with a Matthew coefficient score (MCC) of 0.339 (95% CI: 0.330–0.3483) in cross-validation. The out-of-sample evaluation on the test set yielded an MCC of 0.302. A nomogram evaluating the improvement of KPS post-surgery was built based on statistically significant variables from multivariate logistic regression including clinical and radiomics data (c-index = 0.760, test set). Conclusions: MRI radiomic analysis represents a powerful tool to predict postoperative functional outcomes, as evaluated by KPS. Full article

Background/Objectives: To develop a nomogram for the preoperative prediction of pathologic T3a (pT3a) upstaging in patients with clinical T1(cT1) renal cell carcinoma (RCC). Methods: A total of 169 cT1 patients with RCC with preoperative contrast-enhanced CT (CECT) and clinical data were enrolled in this study. Afterwards, the sample was split randomly into training and testing sets in a 7:3 ratio. Radiomics features were extracted and selected from the whole primary tumor on CECT images to develop radiomics signatures. The nomogram was constructed using the obtained radiomics signature and clinical risk factors. The predictive performance of different models was evaluated and visualized using receiver operator characteristic (ROC) curves. Results: In total, 26 radiomics features were selected for the radiomics signature construction. The radiomics signature yielded area under the curve (AUC) values of 0.945 and 0.873 in the training and testing sets, respectively. The nomogram integrating radiomics signature and predictive clinical factors, including tumor size and neutrophil–lymphocyte ratio (NLR), achieved higher predictive performance in the training [AUC, 0.958; 95% confidence interval (CI): 0.921, 0.995] and testing (AUC, 0.913; 95% CI: 0.814, 1.000) sets. Good calibration was achieved for the nomogram in both the training and testing sets (Brier score = 0.082 and 0.098). Decision curve analysis (DCA) demonstrated that the nomogram was clinically useful in predicting pT3a upstaging, with a corresponding net benefit of 0.378. Conclusions: The proposed nomogram can preoperatively predict pT3a upstaging in cT1 RCC and serve as a non-invasive imaging marker to guide individualized treatment. Full article

This study investigated the relationship between mediastinal fat and pulmonary nodule status, aiming to develop a deep learning-based radiomics model for diagnosing benign and malignant pulmonary nodules. We proposed a combined model using CT images of both pulmonary nodules and the fat around the chest (mediastinal fat). Patients from three centers were divided into training, validation, internal testing, and external testing sets. Quantitative radiomics and deep learning features from CT images served as predictive factors. A logistic regression model was used to combine data from both pulmonary nodules and mediastinal adipose regions, and personalized nomograms were created to evaluate the predictive performance. The model incorporating mediastinal fat outperformed the nodule-only model, with C-indexes of 0.917 (training), 0.903 (internal testing), 0.942 (external testing set 1), and 0.880 (external testing set 2). The inclusion of mediastinal fat significantly improved predictive performance (NRI = 0.243, p < 0.05). A decision curve analysis indicated that incorporating mediastinal fat features provided greater patient benefits. Mediastinal fat offered complementary information for distinguishing benign from malignant nodules, enhancing the diagnostic capability of this deep learning-based radiomics model. This model demonstrated strong diagnostic ability for benign and malignant pulmonary nodules, providing a more accurate and beneficial approach for patient care. Full article

PURPOSE: We aim to compare the performance of three different radiomics models (logistic regression (LR), random forest (RF), and support vector machine (SVM)) and clinical nomograms (Briganti, MSKCC, Yale, and Roach) for predicting lymph node involvement (LNI) in prostate cancer (PCa) patients. MATERIALS AND METHODS: The retrospective study includes 95 patients who underwent mp-MRI and radical prostatectomy for PCa with pelvic lymphadenectomy. Imaging data (intensity in T2, DWI, ADC, and PIRADS), clinical data (age and pre-MRI PSA), histological data (Gleason score, TNM staging, histological type, capsule invasion, seminal vesicle invasion, and neurovascular bundle involvement), and clinical nomograms (Yale, Roach, MSKCC, and Briganti) were collected for each patient. Manual segmentation of the index lesions was performed for each patient using an open-source program (3D SLICER). Radiomic features were extracted for each segmentation using the Pyradiomics library for each sequence (T2, DWI, and ADC). The features were then selected and used to train and test three different radiomics models (LR, RF, and SVM) independently using ChatGPT software (v 4o). The coefficient value of each feature was calculated (significant value for coefficient ≥ ±0.5). The predictive performance of the radiomics models and clinical nomograms was assessed using accuracy and area under the curve (AUC) (significant value for p ≤ 0.05). Thus, the diagnostic accuracy between the radiomics and clinical models were compared. RESULTS: This study identified 343 features per patient (330 radiomics features and 13 clinical features). The most significant features were T2_nodulofirstordervariance and T2_nodulofirstorderkurtosis. The highest predictive performance was achieved by the RF model with DWI (accuracy 86%, AUC 0.89) and ADC (accuracy 89%, AUC 0.67). Clinical nomograms demonstrated satisfactory but lower predictive performance compared to the RF model in the DWI sequences. CONCLUSIONS: Among the prediction models developed using integrated data (radiomics and semantics), RF shows slightly higher diagnostic accuracy in terms of AUC compared to clinical nomograms in PCa lymph node involvement prediction. Full article

Purpose: We aimed to develop a nomogram able to predict treatment failure, skeletal events, and overall survival (OS) in patients with castration-resistant prostate cancer with bone metastases (CRPC-BM) treated with Radium-223 dichloride (²²³Ra). Patients and Methods: Patients from the Castilla-La Mancha Spanish region were prospectively included in the ChoPET-Rad multicenter study from January 2015 to December 2022. Patients underwent baseline, interim, and end-of-treatment bone scintigraphy (BS) and ¹⁸F-Fluorocholine PET/CT (FCH PET/CT) scans, obtaining multiple imaging radiomics as well as clinical and biochemical variables during follow-up and studying their association with the previously defined end-points. Survival analysis was performed using the Kaplan–Meier method and Cox regression. Multivariate logistic and Cox regression models were calculated, and these models were depicted by means of nomograms. Results: Median progression-free survival (PFS) and OS were 4 and 14 months (mo), respectively. The variables that showed independent and significant association with therapeutic failure were baseline alkaline phosphatase (AP) levels (p = 0.022) and the characteristics of BM on the CT portion of PET/CT (p = 0.017). In the case of OS, the significant variables were therapeutic failure (p = 0.038), the number of lines received after ²²³Ra (p < 0.001), average SUVmax (p = 0.002), bone marrow infiltration in FCH PET/CT (p = 0.006), and interim FCH PET/CT response (p = 0.048). Final nomograms included these variables, showing good discrimination among the 100 patients included in our study. In the study of skeletal events, only OS showed a significant association in the multivariate analysis, resulting in an inconsistent nomogram design. Conclusions: FCH PET/CT appears to be a good tool for evaluating patients eligible for treatment with ²²³Ra, as well as for their follow-up. Thus, findings derived from it, such as the morphological characteristics of BM in the CT, bone marrow infiltration, or the response to ²²³Ra in the interim study, have proven to be solid and useful variables in the creation of nomograms for predicting therapeutic failure and OS. Full article

Purpose: The aim of this study was to construct and validate a nomogram for preoperatively predicting perineural invasion (PNI) in gastric cancer based on machine learning, and to investigate the impact of PNI on the overall survival (OS) of gastric cancer patients. Methods: Data were collected from 162 gastric patients and analyzed retrospectively, and radiomics features were extracted from contrast-enhanced computed tomography (CECT) scans. A group of 42 patients from the Cancer Imaging Archive (TCIA) were selected as the validation set. Univariable and multivariable analyses were used to analyze the risk factors for PNI. The t-test, Max-Relevance and Min-Redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO) were used to select radiomics features. Radscores were calculated and logistic regression was applied to construct predictive models. A nomogram was developed by combining clinicopathological risk factors and the radscore. The area under the curve (AUC) values of receiver operating characteristic (ROC) curves, calibration curves and clinical decision curves were employed to evaluate the performance of the models. Kaplan–Meier analysis was used to study the impact of PNI on OS. Results: The univariable and multivariable analyses showed that the T stage, N stage and radscore were independent risk factors for PNI (p < 0.05). A nomogram based on the T stage, N stage and radscore was developed. The AUC of the combined model yielded 0.851 in the training set, 0.842 in the testing set and 0.813 in the validation set. The Kaplan–Meier analysis showed a statistically significant difference in OS between the PNI group and the non-PNI group (p < 0.05). Conclusions: A machine learning-based radiomics–clinicopathological model could effectively predict PNI in gastric cancer preoperatively through a non-invasive approach, and gastric cancer patients with PNI had relatively poor prognoses. Full article

Background: The prognostic value of conducting ¹⁸F-FDG PET/CT imaging has yielded different results in patients with laryngeal cancer and hypopharyngeal cancer, but these results are controversial, and there is a lack of dedicated studies on each type of cancer. This study aimed to evaluate whether combining radiomic analysis of pre- and post-treatment ¹⁸F-FDG PET/CT imaging features and clinical parameters has additional prognostic value in patients with laryngeal cancer and hypopharyngeal cancer. Methods: From 2008 to 2016, data on patients diagnosed with cancer of the larynx and hypopharynx were retrospectively collected. The patients underwent pre- and post-treatment ¹⁸F-FDG PET/CT imaging. The values of ΔPre-Post PET were measured from the texture features. Least absolute shrinkage and selection operator (LASSO) Cox regression was used to select the most predictive features to formulate a Rad-score for both progression-free survival (PFS) and overall survival (OS). Kaplan–Meier curve analysis and Cox regression were employed to assess PFS and OS. Then, the concordance index (C-index) and calibration plot were used to evaluate the performance of the radiomics nomogram. Results: Study data were collected for a total of 91 patients. The mean follow-up period was 71.5 mo. (8.4–147.3). The Rad-score was formulated based on the texture parameters and was significantly associated with both PFS (p = 0.024) and OS (p = 0.009). When predicting PFS, only the Rad-score demonstrated a significant association (HR 2.1509, 95% CI [1.100–4.207], p = 0.025). On the other hand, age (HR 1.116, 95% CI [1.041–1.197], p = 0.002) and Rad-score (HR 33.885, 95% CI [2.891–397.175], p = 0.005) exhibited associations with OS. The Rad-score value showed good discrimination when it was combined with clinical parameters in both PFS (C-index 0.802–0.889) and OS (C-index 0.860–0.958). The calibration plots also showed a good agreement between the observed and predicted survival probabilities. Conclusions: Combining clinical parameters with radiomics analysis of pre- and post-treatment ¹⁸F-FDG PET/CT parameters in patients with laryngeal cancer and hypopharyngeal cancer might have additional prognostic value. Full article

Microglia and macrophages play a major role in glioma immune responses within the glioma microenvironment. We aimed to construct a prognostic prediction model for glioma based on microglia/macrophage-correlated genes. Additionally, we sought to develop a non-invasive radiogenomics approach for risk stratification evaluation. Microglia/macrophage-correlated genes were identified from four single-cell datasets. Hub genes were selected via lasso–Cox regression, and risk scores were calculated. The immunological characteristics of different risk stratifications were assessed, and radiomics models were constructed using corresponding MRI imaging to predict risk stratification. We identified eight hub genes and developed a relevant risk score formula. The risk score emerged as a significant prognostic predictor correlated with immune checkpoints, and a relevant nomogram was drawn. High-risk groups displayed an active microenvironment associated with microglia/macrophages. Furthermore, differences in somatic mutation rates, such as IDH1 missense variant and TP53 missense variant, were observed between high- and low-risk groups. Lastly, a radiogenomics model utilizing five features from magnetic resonance imaging (MRI) T2 fluid-attenuated inversion recovery (Flair) effectively predicted the risk groups under a random forest model. Our findings demonstrate that risk stratification based on microglia/macrophages can effectively predict prognosis and immune functions in glioma. Moreover, we have shown that risk stratification can be non-invasively predicted using an MRI-T2 Flair-based radiogenomics model. Full article